Loading BioAtlas...
Loading BioAtlas...
Comparez modèles biologiques, moteurs de docking et flux de calcul côte à côte. Filtrez par modèle d'accès, empreinte de calcul et catégorie pour parvenir à une table de décision exploitable en moins d'une minute.
| Attribut | ＋ Ajouter un outil | |||
|---|---|---|---|---|
| Category | Biological Foundation Models | Biological AI Models | Biological AI Models | — |
| Subcategory | Variant Effect Prediction | Protein Design | Protein Design | — |
| Company | Meta AI (FAIR) | Pacesa Lab | Boltz Team | — |
| Access mode | Open Source | Research code or publication | Research code or publication | — |
| Licence conditions | MIT License | Check code and model weights separately | Check code and model weights separately | — |
| Compute requirements | 1x GPU (>= 16GB VRAM) for batch scoring | Check selected checkpoint and runtime; no GPU catalog recommendation | Check selected checkpoint and runtime; no GPU catalog recommendation | — |
| Biological application | Predicting viral escape, disease-associated mutations, and enzyme thermostability | Non enregistré | Non enregistré | — |
| Research workflow | Wild-type sequence + candidate mutations -> compute log-likelihood ratio scores | Non enregistré | Non enregistré | — |
| Evidence level | Peer-reviewed research (NeurIPS 2021) | Peer-reviewed primary method | Primary research preprint | — |
| Commercial eligibility | Permissive open source release | Unknown, requires audit | Unknown, requires audit | — |
| Price | Free Open Source | Check selected model licence | Check selected model licence | — |
| Availability ⓘ | Available on GitHub and PyPI | Public research method/code | Public research method/code | — |
| Features | State-of-the-art zero-shot variant effect prediction across 41 deep mutational scanning datasets, Ensemble of five distinct models trained on UniRef90 with different random seeds, Captures epistatic and structural constraints directly from evolutionary sequences, Standard benchmark baseline in computational biology for mutation scoring | AF2-guided optimization pipeline proposes protein binder designs for target structures., Candidate binder sequences, modeled protein complexes | Target-conditioned protein and peptide binder generation model as reported in its preprint., Binder sequence and structure candidates | — |
| Entry type | AI Model | Research AI model / method | Research AI model / method | — |
| AI role | Variant Effect Prediction | Published biomedical AI method | Published biomedical AI method | — |
| Input data | Non enregistré | Target protein 3D coordinates; AF2/MPNN workflow and target interface constraints | Target context; design constraints | — |
| Output data | Non enregistré | Candidate binder sequences; modeled protein complexes | Binder sequence and structure candidates | — |
| Validation | Non enregistré | Requires independent dataset-specific evaluation | Requires independent dataset-specific evaluation | — |
| Type | Masked protein language model ensemble | Non enregistré | Non enregistré | — |
| Intended use | Non enregistré | Non enregistré | Non enregistré | — |
| Compatibility | Non enregistré | Non enregistré | Non enregistré | — |
| Manufacturer | Meta AI | Non enregistré | Non enregistré | — |
| Integration evidence | https://github.com/facebookresearch/esm | Non enregistré | Non enregistré | — |
| Laboratory handoff | Guides directed evolution and deep mutational scanning library design | Non enregistré | Non enregistré | — |